What are the runtime requirements?
Node.js v18+ (for NPX/source install) or Docker (for Docker install). A LIFX API token is required.
@furey
Basic information
🤖💡 MCP Server for LIFX API
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"lifx-api-mcp-server": {
"command": "npx",
"args": [
"-y",
"lifx-api-mcp-server@latest"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
LIFX API MCP Server is a local Model Context Protocol (MCP) server that provides access to LIFX smart devices using natural language via LLMs. It allows users to list lights, set states, activate scenes, and trigger effects through the LIFX HTTP API.
Obtain a LIFX API token from the LIFX Cloud settings page. Install the server via npx (npx -y lifx-api-mcp-server@latest) or Docker (docker run --rm -i --network=host furey/lifx-api-mcp-server). Configure the token using a config file (~/.lifx-api-mcp-server.jsonc), environment variable (CONFIG_API_TOKEN), or command-line argument. Set up an MCP client (e.g., Claude Desktop) and control lights using natural language. Use resources like lifx://lights and prompts like effect-creator.
Node.js v18+ (for NPX/source install) or Docker (for Docker install). A LIFX API token is required.
Set it via the config file (`apiToken` field in `~/.lifx-api-mcp-server.jsonc`), environment variable (`CONFIG_API_TOKEN`), or command-line argument (least recommended). Priority follows that order.
No. The server does not store or cache information permanently; all device data remains in the LIFX cloud.
It uses stdio transport, as shown in the startup log output ("Creating stdio transport").
Yes. Use the `disabled` or `enabled` keys in the config file to selectively disable or limit components.

discoverGPT is visualAI's MCP gateway for AI commerce: one connection gives Claude 40 tools spanning product search, data-quality review, AI-discovery feeds, and virtual try-on, all backed by a single canonical product c

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Comments